Emadeldeen Eldele
Emadeldeen Eldele
you are welcome! I created this [gist](https://gist.github.com/emadeldeen24/5ee33e6931f94e0547052b444fda85f6) to make easier for anyone to use.
> @Emadeldeen-24 I get the segmentation fault when I use the file you provided. why? > In the line of the code > `model['tri'] = model['tri'].T.copy(order='C').astype(np.int32) - 1` > >...
> > you are welcome! > > I created this [gist](https://gist.github.com/Emadeldeen24/5ee33e6931f94e0547052b444fda85f6) to make easier for anyone to use. > > HI，did you delete this [gist], I cannot find any info...
In line 228 in `train.py` update the code to become: x = Convolution2D(n_filters, (kH, kW), subsample=(sH, sW), border_mode=border_mode, init=init_conv, data_format = 'channels_first')(x)
you are welcome!
@vkclsys https://1drv.ms/f/s!Av3OKFp7SF0bmRJjYGEa6ujkD2RO?e=DL3F3D
They have been reported and auto-deleted from the drive for some reason. Kindly find the 3 files here: https://1drv.ms/f/s!Av3OKFp7SF0bmRJjYGEa6ujkD2RO?e=DL3F3D
check the activation function ... here it uses Sigmoid .. according to your problem you may need to change it maybe to ReLU
Hi, thanks for experimenting with our code. Unfortunately, I don't have the logs anymore. But I recall using the same parameters as yours, maybe the dropout was 0.5, but everything...